改进ROEWA与小波变换结合的遥感图像海陆分离

海陆分离一直是光学遥感图像舰船检测中最重要的一部分，目前大多数的海陆分离算法都是依靠先验信息或是利用灰度特征对图像进行处理，造成分割效果不明显，大量的孤立区域无法处理，而且会造成误分割，不利于后续处理。针对上述问题，本文提出一种基于改进ROEWA算子与小波变换结合的海陆分离方法。首先利用ROEWA(指数加权平均比率)算子对原始图像进行边缘检测得到边缘的强度，再利用非极值抑制和双阈值算法定位边缘，然后采用小波变换对叠加后的图像进行二次边缘提取，提取边缘的方向，最后对边缘检测后的图像进行区域生长，进而得到最终的海陆分离图像。实验结果表明，本文的算法与常用的的海陆分离算法相比，检测效率和精度都比较高，且鲁棒性好，有利于后续舰船检测的处理。

Improved ROEWA operator combined with wavelet transform for sea-land segmentation in remote sensing image

The sea-land segmentation is always the most important part of ship detection in optical remote sensing image,most sea-land segmentation algorithms may result in wrong segmentations or lots of isolates ares due to the use of single feature for image processing,which makes it difficult for subsequent processing.To solve the problem,an improved algorithm is proposed, which combines Roewa operator with wavelet transform operator . First, the edge of the original image is detected by ROEWA operator to get the edge intensity.secondly, Locating the edge by using the non extreme suppression and double threshold algorithm,thirdly, the wavelet transform is used to extract the edges of the obtained image, extracting the edge of direction.Finally,the result of segmentation after regional growth was attained. The experimental results show that this algorithm can segment the sea and land and shield the land exactly and effectively,and can also make it convenience for subsequent processes.